Triple
T6551827
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | District of Borken |
E151146
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Reken
Reken is a municipality in the western German state of North Rhine-Westphalia, known for its rural character and location within the Münsterland region.
|
E604603
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Reken | Statement: [District of Borken, contains, Reken]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Reken Context triple: [District of Borken, contains, Reken]
-
A.
Reknes
Reknes is a small island located near the town of Molde on Norway’s western coast.
-
B.
Randenbroek
Randenbroek is a historic estate near Amersfoort in the Netherlands, known as the place where the Dutch Golden Age architect and painter Jacob van Campen spent his final years.
-
C.
Blokzijl
Blokzijl is a historic former trading town and harbor in the Dutch province of Overijssel, known for its picturesque canals and well-preserved old center.
-
D.
Ekeren
Ekeren is a northern district of the Belgian city of Antwerp, known for its residential character and green spaces.
-
E.
Kwintsheul
Kwintsheul is a village in the Dutch province of South Holland, known for its greenhouse horticulture and location within the Westland region.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Reken Triple: [District of Borken, contains, Reken]
Generated description
Reken is a municipality in the western German state of North Rhine-Westphalia, known for its rural character and location within the Münsterland region.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Reken Target entity description: Reken is a municipality in the western German state of North Rhine-Westphalia, known for its rural character and location within the Münsterland region.
-
A.
Reknes
Reknes is a small island located near the town of Molde on Norway’s western coast.
-
B.
Randenbroek
Randenbroek is a historic estate near Amersfoort in the Netherlands, known as the place where the Dutch Golden Age architect and painter Jacob van Campen spent his final years.
-
C.
Blokzijl
Blokzijl is a historic former trading town and harbor in the Dutch province of Overijssel, known for its picturesque canals and well-preserved old center.
-
D.
Ekeren
Ekeren is a northern district of the Belgian city of Antwerp, known for its residential character and green spaces.
-
E.
Kwintsheul
Kwintsheul is a village in the Dutch province of South Holland, known for its greenhouse horticulture and location within the Westland region.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69c687f3fd60819083bfa583e5bcfa71 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6ae05cd988190a013226b14cd98f0 |
completed | March 27, 2026, 4:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6d55416e48190b574e37a6f2e6690 |
completed | March 27, 2026, 7:07 p.m. |
| NEDg | Description generation | batch_69c6d6acc2208190ac47c60bb896c1cd |
completed | March 27, 2026, 7:12 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c6d83b53e48190881a3e1e8fa8b168 |
completed | March 27, 2026, 7:19 p.m. |
Created at: March 27, 2026, 1:51 p.m.